Intology's Locus autonomously builds molecular design models that beat SOTA expert solutions
yusufroohani · x · 2026-11-04
Intology unveiled Locus, an automated research system that develops scientific AI models claimed to outperform SOTA expert solutions while autonomously leveraging proprietary data.
Validated across several molecular scoring and design tasks:
- Training molecular property prediction models for a proprietary task;
- Fine-tuning Boltz-2 to predict small-molecule potency;
- Building antibody design workflows around BoltzGen, Boltz-2, ESMC, and ESMFold.
These are real-world AI-for-science use cases where tasks are often out-of-distribution for existing foundation models; the team says Locus improves models end-to-end autonomously.
Related event: Intology Unveils Locus, an Autonomous Scientific Discovery System(14 posts)→
More from Research
- Stanford team forecasts GSM8K accuracy within 3 pts using 5600x less compute — stanfordnlp · 2026-11-04
- A 1995 Pentium running modern Stockfish would beat Kasparov: software worth 720 Elo — demian_ai · 2026-11-04
- History Forcing: Zhejiang U & Microsoft Fix Long-Horizon Drift in Video World Models — ZhejiangUniversity · 2026-11-04
- D&A: Decoupling Description from Assessment Turns Any VLM into a Robot Reward Model — weichiuma · 2026-11-04
- Muon beats AdamW in pretraining loss, but AdamW wins after finetuning at scale — AdtRaghunathan · 2026-11-04
- Vorelios (YC F26) launches AI that predicts physics in seconds to engineer designs autonomously — KlausCodes · 2026-11-04